相关论文: Video-Thinker: Sparking "Thinking with Videos" via…

Temporal Video Grounding (TVG) aims to precisely localize video segments corresponding to natural language queries, which is a critical capability for long-form video understanding. Although existing reinforcement learning approaches…

The "thinking with images" paradigm represents a pivotal shift in the reasoning of Vision Language Models (VLMs), moving from text-dominant chain-of-thought to image-interactive reasoning. By invoking visual tools or generating intermediate…

The goal of text-to-video retrieval is to search large databases for relevant videos based on text queries. Existing methods have progressed to handling explicit queries where the visual content of interest is described explicitly; however,…

Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to…

Large Audio-Language Models (LALMs) have made significant progress in audio understanding, yet they primarily operate as perception-and-answer systems without explicit reasoning processes. Existing methods for enhancing audio reasoning rely…

The remarkable natural language understanding, reasoning, and generation capabilities of large language models (LLMs) have made them attractive for application to video understanding, utilizing video tokens as contextual input. However,…

Chain-of-Thought (CoT) reasoning excels in language models but struggles in vision-language models due to premature visual-to-text conversion that discards continuous information such as geometry and spatial layout. While recent methods…

Despite advances in reinforcement learning (RL)-based video reasoning with large language models (LLMs), data collection and fine-tuning remain significant challenges. These methods often rely on large-scale supervised fine-tuning (SFT)…

Multimodal Large Language Models (MLLMs) have made rapid progress in perception, understanding, and reasoning, yet existing benchmarks fall short in evaluating these abilities under continuous and dynamic real-world video streams. Such…

While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs). As a result, most LMMs default to verbalizing perceptual content into text, a strong limitation for tasks…

Recent studies have demonstrated the efficacy of using Reinforcement Learning (RL) in building reasoning models that articulate chains of thoughts prior to producing final answers. However, despite ongoing advances that aim at enabling…

DeepSeek-R1-Zero has successfully demonstrated the emergence of reasoning capabilities in LLMs purely through Reinforcement Learning (RL). Inspired by this breakthrough, we explore how RL can be utilized to enhance the reasoning capability…

Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for complex reasoning tasks. However, two critical limitations…

Learning general-purpose reasoning capabilities has long been a challenging problem in AI. Recent research in large language models (LLMs), such as DeepSeek-R1, has shown that reinforcement learning techniques like GRPO can enable…

Reinforcement learning (RL) has emerged as a promising approach for eliciting reasoning chains before generating final answers. However, multimodal large language models (MLLMs) generate reasoning that lacks integration of visual…

Recently, Multimodal Large Language Models (MLLMs) have demonstrated significant potential in complex visual tasks through the integration of Chain-of-Thought (CoT) reasoning. However, in Video Question Answering, extended thinking…

Online Video Large Language Models (VideoLLMs) play a critical role in supporting responsive, real-time interaction. Existing methods focus on streaming perception, lacking a synchronized logical reasoning stream. However, directly applying…

Large Reasoning Models (LRMs) have achieved remarkable performance on complex reasoning tasks by adopting the ``think-then-answer'' paradigm, which enhances both accuracy and interpretability. However, current LRMs exhibit two critical…

Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models, yet existing video reasoning methods often rely on coarse sequence-level rewards or single-factor token selection,…

Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning traces for interpretability; however, their reasoning often appears convincing while…